© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 608
    Prev
    Next
    INDEX
    Explanations

    library dependencies

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on multi‐digit numeric tokens (especially longer numbers or decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    チュラル
    0.61
    affaire
    0.53
    fq
    0.52
    Лі
    0.51
    odnev
    0.51
    喿
    0.49
    NewUrl
    0.49
    articolo
    0.49
    谘
    0.49
     Лі
    0.48
    POSITIVE LOGITS
     گئیں
    0.55
     seperti
    0.50
     várias
    0.50
     xWidth
    0.50
     때는
    0.48
     olsa
    0.47
     wú
    0.47
     Kalman
    0.47
    ،
    0.46
     langs
    0.46
    Activations Density 0.000%

    No Known Activations